INDEX

Explanations

references to toxins and poisoning

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 كومونز

-1.13

makeConstraints

-0.92

termilk

-0.84

 Heuer

-0.77

onedDateTime

-0.75

AccessorTable

-0.75

 Gaulle

-0.75

conuts

-0.75

ethene

-0.74

WRP

-0.74

POSITIVE LOGITS

poison

1.56

 poison

1.54

 Poison

1.53

 poisoning

1.40

Poison

1.39

 poisoned

1.23

 poisons

1.17

 poisonous

1.12

毒

0.98

 veneno

0.88

Activations Density 0.012%

references to toxins and poisoning

No Comments

No Known Activations